Building Energy Modeling using Non-Linear Auto Regression Neural Networks
The paper discusses the modeling methodologies for building energy system using non-linear auto regression
artificial neural networks. The model predicts whole building energy consumptions as a function of four input variables, dry
bulb and wet bulb outdoor air temperatures, hour of day and type of day. To train and test the models, data from two existing
buildings and from simulations are collected and used. The data are pre-processing using wavelet basis to remove the noise
and anomalies. Different neural network structures are then tested along with various input delays to determine the one
yielding the best results. The results show that the model can predict the energy consumptions accurately and it can be then
used for various energy efficiency and saving estimation applications.
Keywords - Building Energy Model, Neural Network, Wavelet Transfer, HVAC System, Regression Model.